Repository navigation
Fix DDLA GPU compilation - #14
Merged
PeizeLin merged 2 commits intoOct 22, 2026
Merged
Conversation
Contributor
|
Agreed. My local branch has verified the same fix. |
Contributor
|
I agree with the device_check fix, the Ds_result_thread need @PeizeLin 's review |
Stardust0831
force-pushed
the
fix/gpu-ddla-accumulation
branch
from
October 21, 2026 16:37
155fa24 to
e2f92bc
Compare
Stardust0831
changed the title
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
4 participants
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
The DDLA GPU path fails to compile against DDLA v0.0.4 due to an incorrect function name and a stale cleanup call.
ddla::DEVICE_CHECKcalls incorrectly renamed in 123517d.destroy_lock_resultwithdestroy_lockanddestroy_Ds_result, following the helper split in 6ce3c84.Validated CPU-only and DDLA v0.0.4/CUDA builds on an NVIDIA V100 with GCC 13.3. Standalone tests checked all 18 contractions with the default
fac_add_Ds = 1, empty and seeded outputs,float,double,complex<float>andcomplex<double>, and 1/4 OpenMP threads. Both CPU modes and the GPU mode passed.Signed and scaled accumulation requires a separate fix.
Related: deepmodeling/abacus-develop#8169.